PG3: Policy-Guided Planning for Generalized Policy Generation.

Ryan Yang Tom Silver Aidan Curtis Tomás Lozano-Pérez Leslie Pack Kaelbling

Published in: IJCAI (2022)

Keyphrases

optimal policy
action selection
reinforcement learning problems
asymptotically optimal
sequential decision making
policy making
neural network
decision support
planning problems
infinite horizon
partially observable
access control policies
partially observable markov decision processes
management policies